def decode_data(data, encoding_guess, can_be_binary=True):
"""Given string data, return an (is_text, data) tuple, where data is
returned as unicode if we think it's text and were able to determine an
encoding for it.
If can_be_binary is False, then skip the initial is_binary check.
"""
if not (can_be_binary and is_binary_string(data[:1024])):
try:
# Try our default encoding.
data = data.decode(encoding_guess)
return True, data
except UnicodeDecodeError:
# Fall back to chardet - chardet is really slow, which is why we
# don't just do chardet from the start.
detector = UniversalDetector()
for chunk in ichunks(80, data):
detector.feed(chunk)
if detector.done:
break
detector.close()
if detector.result['encoding']:
try:
data = data.decode(detector.result['encoding'])
return True, data
except (UnicodeDecodeError, LookupError):
# Either we couldn't decode or chardet gave us an encoding
# that python doesn't recognize (yes, it can do that).
pass # Leave data as str.
return False, data
def decode_data(data, encoding_guess, can_be_binary=True):
"""Given string data, return an (is_text, data) tuple, where data is
returned as unicode if we think it's text and were able to determine an
encoding for it.
If can_be_binary is False, then skip the initial is_binary check.
"""
if not (can_be_binary and is_binary_string(data[:1024])):
try:
# Try our default encoding.
data = data.decode(encoding_guess)
return True, data
except UnicodeDecodeError:
# Fall back to chardet - chardet is really slow, which is why we
# don't just do chardet from the start.
detector = UniversalDetector()
for chunk in ichunks(80, data):
detector.feed(chunk)
if detector.done:
break
detector.close()
if detector.result['encoding']:
try:
data = data.decode(detector.result['encoding'])
return True, data
except (UnicodeDecodeError, LookupError):
# Either we couldn't decode or chardet gave us an encoding
# that python doesn't recognize (yes, it can do that).
pass # Leave data as str.
return False, data
def mapper(text='gatsby'):
"""Splits a problem into a number of small tasks"""
import os
fname = os.path.join(os.path.dirname(__file__), 'map_reduce2-{text}.txt'.format(text=text))
with open(fname, 'r') as f:
paralleled_problem = []
for c in ichunks(50, f):
paralleled_problem.append(m.s(' '.join(map(lambda t: t.decode('utf-8'), c))))
return (chord(paralleled_problem, g.s() | r.s())).delay()
def mergesort(filename, output=None, key=None, maxitems=1e6, progress=True):
"""Given an input file sort it by performing a merge sort on disk.
:param filename: Either a filename as a ``str`` or a ``py._path.local.LocalPath`` instance.
:type filename: ``str`` or ``py._path.local.LocalPath``
:param output: An optional output filename as a ``str`` or a ``py._path.local.LocalPath`` instance.
:type output: ``str`` or ``py._path.local.LocalPath`` or ``None``
:param key: An optional key to sort the data on.
:type key: ``function`` or ``None``
:param maxitems: Maximum number of items to hold in memory at a time.
:type maxitems: ``int``
:param progress: Whether or not to display a progress bar
:type progress: ``bool``
This uses ``py._path.local.LocalPath.make_numbered_dir`` to create temporry scratch space to work
with when splitting the input file into sorted chunks. The mergesort is processed iteratively in-memory
using the ``~merge`` function which is almost identical to ``~heapq.merge`` but adds in the support of
an optional key function.
"""
p = filename if isinstance(filename, LocalPath) else LocalPath(filename)
output = p if output is None else output
key = key if key is not None else lambda x: x
scratch = LocalPath.make_numbered_dir(prefix="mergesort-")
nlines = sum(1 for line in p.open("r"))
# Compute a reasonable chunksize < maxitems
chunksize = first(ifilter(lambda x: x < maxitems, imap(lambda x: nlines / (2**x), count(1))))
# Split the file up into n sorted files
if progress:
bar = ProgressBar("Split/Sorting Data", max=(nlines / chunksize))
for i, items in enumerate(ichunks(chunksize, jsonstream(p))):
with scratch.ensure("{0:d}.json".format(i)).open("w") as f:
f.write("\n".join(map(dumps, sorted(items, key=key))))
if progress:
bar.next()
if progress:
bar.finish()
q = scratch.listdir("*.json")
with output.open("w") as f:
if progress:
bar = ProgressBar("Merge/Sorting Data", max=nlines)
for item in merge(*imap(jsonstream, q)):
f.write("{0:s}\n".format(dumps(item)))
if progress:
bar.next()
if progress:
bar.finish()
def path_chunks(tree):
"""Return an iterable of worker-sized iterables of paths."""
return ichunks(500, unignored(tree.source_folder,
tree.ignore_paths,
tree.ignore_filenames))
def path_chunks(tree):
"""Return an iterable of worker-sized iterables of paths."""
return ichunks(
500,
unignored(tree.source_folder, tree.ignore_paths,
tree.ignore_filenames))
def render_recent_collections_block(limit=10):
""" Renders last block with last collections for index page.
"""
qs = Collection.objects.all().order_by('-id')[:limit]
videos_chunks = ichunks(2, qs)
return locals()
def render_recent_galleries_block(limit=10):
""" Renders last galleries block for index page.
"""
qs = Gallery.objects.all().order_by('-id')[:limit]
galleries_chunks = ichunks(2, qs)
return locals()
